{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T01:50:26Z","timestamp":1768701026413,"version":"3.49.0"},"reference-count":30,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2020,2,26]],"date-time":"2020-02-26T00:00:00Z","timestamp":1582675200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>This paper focuses on the time series prediction problem for underflow concentration of deep cone thickener. It is commonly used in the industrial sedimentation process. In this paper, we introduce a dual attention neural network method to model both spatial and temporal features of the data collected from multiple sensors in the thickener to predict underflow concentration. The concentration is the key factor for future mining process. This model includes encoder and decoder. Their function is to capture spatial and temporal importance separately from input data, and output more accurate prediction. We also consider the domain knowledge in modeling process. Several supplementary constructed features are examined to enhance the final prediction accuracy in addition to the raw data from sensors. To test the feasibility and efficiency of this method, we select an industrial case based on Industrial Internet of Things (IIoT). This Tailings Thickener is from FLSmidth with multiple sensors. The comparative results support this method has favorable prediction accuracy, which is more than 10% lower than other time series prediction models in some common error indices. We also try to interpret our method with additional ablation experiments for different features and attention mechanisms. By employing mean absolute error index to evaluate the models, experimental result reports that enhanced features and dual-attention modules reduce error of fitting ~5% and ~11%, respectively.<\/jats:p>","DOI":"10.3390\/s20051260","type":"journal-article","created":{"date-parts":[[2020,2,27]],"date-time":"2020-02-27T03:21:16Z","timestamp":1582773676000},"page":"1260","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["A Dual-Attention Recurrent Neural Network Method for Deep Cone Thickener Underflow Concentration Prediction"],"prefix":"10.3390","volume":"20","author":[{"given":"Zhaolin","family":"Yuan","sequence":"first","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science &amp; Technology Beijing, Beijing 100083, China"}]},{"given":"Jinlong","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science &amp; Technology Beijing, Beijing 100083, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6896-0572","authenticated-orcid":false,"given":"Di","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of ICT and Natural Science, Norwegian University of Science and Technology, 6009 \u00c5lesund, Norway"}]},{"given":"Xiaojuan","family":"Ban","sequence":"additional","affiliation":[{"name":"School of Computer and Communication Engineering, University of Science &amp; Technology Beijing, Beijing 100083, China"}]}],"member":"1968","published-online":{"date-parts":[[2020,2,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Jeschke, S., Brecher, C., Song, H., and Rawat, D.B. (2017). Erratum to: Industrial Internet of Things. Ind. Internet Things, 1.","DOI":"10.1007\/978-3-319-42559-7_30"},{"key":"ref_2","first-page":"1","article-title":"Online reinforcement learning control algorithm for concentration of thickener underflow","volume":"45","author":"Yuan","year":"2019","journal-title":"Acta Autom. Sin."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.mineng.2018.11.006","article-title":"Dynamic modeling and simulation of tailing thickener units for the development of control strategies","volume":"131","author":"Langlois","year":"2019","journal-title":"Miner. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jprocont.2015.02.002","article-title":"Studies on parameter estimation and model predictive control of paste thickeners","volume":"28","author":"Tan","year":"2015","journal-title":"J. Process. Control."},{"key":"ref_5","first-page":"13","article-title":"Research on a method for predicting the underflow concentration of a thickener based on the hybrid model","volume":"14","author":"Xiao","year":"2020","journal-title":"Eng. Appl. Comput. Fluid Mech."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1016\/j.ifacol.2016.10.249","article-title":"Sparse Identification of Nonlinear Dynamics with Control (SINDYc)","volume":"49","author":"Brunton","year":"2016","journal-title":"IFAC-PapersOnLine"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.ins.2011.12.031","article-title":"Data-driven based model for flow prediction of steam system in steel industry","volume":"193","author":"Liu","year":"2012","journal-title":"Inf. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2454","DOI":"10.1109\/78.852025","article-title":"Autoregressive model orders for Durbin\u2019s MA and ARMA estimators","volume":"48","author":"Broersen","year":"2000","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1016\/j.jhydrol.2012.11.017","article-title":"Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir","volume":"476","author":"Valipour","year":"2013","journal-title":"J. Hydrol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_11","first-page":"676","article-title":"Study on the thickening properties of unclassified tailings and its application to thickener design","volume":"6","author":"Wang","year":"2011","journal-title":"J. Univ. Sci. Technol. Beijing"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.mineng.2017.01.011","article-title":"A study on model predictive control in paste thickeners with rake torque constraint","volume":"105","author":"Tan","year":"2017","journal-title":"Miner. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wu, D., Wang, H., and Seidu, R. (2019, January 3\u20137). Collaborative Analysis for Computational Risk in Urban Water Supply Systems. Proceedings of the 28th ACM International Conference on Information and Knowledge Management, New York, NY, USA.","DOI":"10.1145\/3357384.3358133"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Wu, D., Wang, H., Mohammed, H., and Seidu, R. (2019). Quality Risk Analysis for Sustainable Smart Water Supply Using Data Perception. IEEE Trans. Sustain. Comput.","DOI":"10.1109\/TSUSC.2019.2929953"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3339308","article-title":"Lightweight Convolution Neural Networks for Mobile Edge Computing in Transportation Cyber Physical Systems","volume":"10","author":"Zhou","year":"2019","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3337065","article-title":"Big Data Analytics for Large-scale Wireless Networks: Challenges and Opportunities","volume":"52","author":"Dai","year":"2019","journal-title":"ACM Comput. Surv."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1007\/s12559-014-9255-2","article-title":"An Insight into Extreme Learning Machines: Random Neurons, Random Features and Kernels","volume":"6","author":"Huang","year":"2014","journal-title":"Cogn. Comput."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"23551","DOI":"10.1109\/ACCESS.2018.2825538","article-title":"LSTM-Based Analysis of Industrial IoT Equipment","volume":"6","author":"Zhang","year":"2018","journal-title":"IEEE Access"},{"key":"ref_19","first-page":"759","article-title":"A dual-stage two-phase model of selective attention","volume":"3","author":"Steinhauser","year":"2010","journal-title":"Psychol. Rev."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Nunez, F., Langarica, S., Diaz, P., Torres, M., and Salas, J.C. (2019). Neural Network-Based Model Predictive Control of a Paste Thickener over an Industrial Internet Platform. IEEE Trans. Ind. Inf.","DOI":"10.1109\/TII.2019.2953275"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1007\/s12555-010-0418-y","article-title":"Feature enhancement of medical images using morphology-based homomorphic filter and differential evolution algorithm","volume":"8","author":"Oh","year":"2010","journal-title":"Int. J. Control. Autom. Syst."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.minpro.2015.01.007","article-title":"An intelligent control strategy for thickening process","volume":"142","author":"Xu","year":"2015","journal-title":"Int. J. Miner. Process."},{"key":"ref_23","unstructured":"Bahdanau, D., Cho, K.H., and Bengio, Y. (2015, January 7\u20139). Neural machine translation by jointly learning to align and translate. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015)\u2014 Conference Track Proceedings, San Diego, CA, USA."},{"key":"ref_24","unstructured":"Merri, B.V. (2014). On the Properties of Neural Machine Translation: Encoder\u2013Decoder Approaches. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Qin, Y., Song, D., Cheng, H., Cheng, W., Jiang, G., and Cottrell, G.W. (2017). A dual-stage attention-based recurrent neural network for time series prediction. Int. Joint Conf. Artif. Intell., 2627\u20132633.","DOI":"10.24963\/ijcai.2017\/366"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tian, Y., Kong, Y., Zhong, B., and Fu, Y. (2018). Residual Dense Network for Image Restoration. IEEE Trans. Pattern Anal. Mach. Intell.","DOI":"10.1109\/CVPR.2018.00262"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely connected convolutional networks. Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_28","unstructured":"Kingma, D.P., and Ba, J.L. (2015, January 7\u20139). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015 - Conference Track Proceedings, San Diego, CA, USA."},{"key":"ref_29","unstructured":"Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst., 3147\u20133155."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhou, Y., and Huang, Y. (2018, January 10\u201313). Context Aware Flow Prediction of Bike Sharing Systems. Proceedings of the 2018 IEEE International Conference on Big Data, Seattle, WA, USA.","DOI":"10.1109\/BigData.2018.8621918"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/5\/1260\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:01:47Z","timestamp":1760173307000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/5\/1260"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,26]]},"references-count":30,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2020,3]]}},"alternative-id":["s20051260"],"URL":"https:\/\/doi.org\/10.3390\/s20051260","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,26]]}}}